Integration

Claude export: what it contains

Official Claude export with JSON shape detection

Supported data

Conversation timestamps and message counts are parsed locally with adapter warnings for unknown shapes.

Privacy

Raw prompts, responses, attachments, local paths, and source files stay on your device in either privacy mode. The only thing stats-with-titles adds is the conversation title.

Limitations

Provider export formats may change. Unknown fields are preserved as warnings instead of silently invented metrics.

Duplicate prevention

Re-imports use stable provider session identity and content normalization hashes. Container file checksums never define session identity.

Metric quality

Unavailable values remain null. Estimates are labelled estimated and exact values are never fabricated.

Troubleshooting

If detection fails, use the preview warnings and confirm the export source/version before importing again.

What a Claude export can tell you

Prompts: Available; Counted from the human turns in `chat_messages`.
Responses: Available; Counted from the assistant turns in `chat_messages`.
Tool calls: Sometimes; Current Claude exports spell out every assistant content block, and `tool_use` blocks are counted from them. An older export that carries message text only leaves this unavailable rather than reporting zero.
Agents launched: Not in export; Claude account exports contain no subagent launches.
Tokens: Not in export; Token usage is genuinely absent from the Claude account export. It is not a parsing gap waiting to be closed.
API-equivalent cost: Not in export; Cost is priced from token counts, and this export carries none. A figure invented without them would be guesswork wearing a currency symbol.
Models: Sometimes; Read from a message's model field when a Claude export records one. The current reference export omitted that field, so those sessions remain unavailable rather than being attributed to a guessed model.
Summed session span: Available; First to last message instant in the conversation. It can include idle gaps.
AI active time: Sometimes; Derived from the union of the start and stop instants Claude stamps on each assistant content block. Blocks that overlap are counted once, so interleaved thinking and tool work is not double counted. Exports without those blocks leave it unavailable.
Estimated interaction time: Available; Estimated from the gaps between consecutive turns, with each gap capped so an overnight pause cannot inflate it.
User active time: Not in export; No export records how long you spent reading or typing. It could only be inferred by subtracting one estimate from another, and an inferred number shown as a measurement would be a fabrication.
Waiting time: Shown as AI active time; Waiting on the model is exactly the AI active time already shown. Repeating it under a second name would add a tile, not a measurement.
Project grouping: Available; Sessions are grouped under a provider inbox: this export names no repository or workspace to group by.